Skip to content
Trending eventHistorical event

MOON: Learning When to Forget and How to Move On in Vision-and-Language Navigation

1 reports1 reporting sourcesUpdated 7 days ago

Overview

Event synthesis

This research presents MOON, a framework that equips frozen vision-and-language navigation policies with lightweight modules for detecting deviations and recovering from them. By clearing visual history upon deviation detection and training a recovery policy via GRPO, MOON improves success rates on R2R-CE and RxR-CE benchmarks by 5.2 and 6.0 points respectively, outperforming compared methods without retraining the base policy.

Generated from attributed reports · Updated 1 hours ago

Event evidence and corrections

0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.

Artifact availability · code: available
Supporting report

“d. Without retraining, MOON also improves zero-shot object-goal navigation on HM3D-OVON. Together, these results suggest that deviation recovery depends on knowing when to forget, not only how to act. Code is available at https://github.com/AutoLab-SAI-SJTU/MOON.”

Exact source · revision 2

Source owner not reported

Evidence dependency changes (2)
  • 2026-11-02T19:19:27.253Z · evidence updated · source revision 2. Evidence extraction was updated; current source attributions are shown above.
  • 2026-10-27T22:14:48.260Z · evidence updated · source revision 1. Evidence extraction was updated; current source attributions are shown above.

Report timeline

Follow attributed reports and material updates.

10/27
  1. arXiv Robotics — research abstractsSignal
    MOON: Learning When to Forget and How to Move On in Vision-and-Language Navigation

    This research presents MOON, a framework that equips frozen vision-and-language navigation policies with lightweight modules for detecting deviations and recovering from them. By clearing visual history upon deviation detection and training a recovery policy via GRPO, MOON improves success rates on R2R-CE and RxR-CE benchmarks by 5.2 and 6.0 points respectively, outperforming compared methods without retraining the base policy.

Timezone · UTC

Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).